03/JOURNAL

Journal

Dated writing on operations, products, software, and decisions. Browse by category or tag.

Matching: 146 / 146 · Newest first

Not Every Improvement Needs a New Skill

Before adding another Skill, determine whether the request needs a patch, a checklist, a reusable capability, or a genuinely separate boundary.

AI & Software
ReflectionRead article

The Chat Ended. The Project Didn't.

Long-running work needs a durable checkpoint, a decision trail, and one safe next action that survives the chat window.

AI & Software
ReflectionRead article

Who Gets the Final Word in an AI Team?

A useful AI team separates the roles of routing, doing, reviewing, and authorizing rather than pretending every agent has final authority.

AI & Software
ReflectionRead article

Why a File Named FINAL Isn't Final

Version names, current-source identity, and actual release evidence are different things—and confusing them multiplies uncertainty.

AI & Software
ReflectionRead article

Does a Green Test Prove the System Works?

A passing static check isn't the same evidence as a working application, a browser test, or a verified production release.

AI & Software
ReflectionRead article

A Workspace Without a Map Is a Maze

When files, specialists, and decisions multiply, a workspace needs a map of relationships rather than just a bigger folder tree.

AI & Software
ReflectionRead article

Can a ZIP File Carry Trust?

A package can carry manifests, file hashes, and provenance—but those are not the same as proving its software works.

AI & Software
ReflectionRead article

A Hundred Experts. Who Chooses the Right One?

As AI specialists multiply, choosing the right owner becomes as important as the quality of any individual expert.

AI & Software
ReflectionRead article

Is Another Expert Really Progress?

The urge to create a new AI expert for every problem—and the discipline of improving the system before expanding it.

AI & Software
ReflectionRead article